Closed-Loop Wearable Sensor and Method

The present application is a continuation of and claims the benefit of co-pending U.S. patent application Ser. No. 18/121,640, filed Mar. 15, 2023, allowed, which claims the benefit of and priority to U.S. Provisional Patent Application No. 63/321,737 , filed Mar. 20, 2022, the entire contents of each of which are incorporated by reference herein.

Embodiments described herein generally relate to systems and methods for sensing physiological parameters and, more particularly but not exclusively, to systems and methods for detecting certain behavior based on physiological parameters.

More than 1 out of 10 people suffer from acute or chronic itch. While itch causes significant morbidity, there are no technologies that accurately, objectively, and continuously assess itch by quantifying scratch (or other physiological symptoms or activities) in a user's natural environment. Accordingly, therapeutic options remain limited.

Also, existing techniques rely on communicating sensor-obtained data to a remote location for analysis. This contributes to lag and a delay in analysis performance.

A need exists, therefore, for systems and methods that overcome the disadvantages associated with existing techniques.

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description section. This summary is not intended to identify or exclude key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

According to one aspect, embodiments relate to an electronic device for measuring motion and acoustic signatures of physiological processes of a human subject. The electronic device comprises an inertial measurement unit (IMU) configured to be operably in direct mechanical communication with the skin of the subject, a microcontroller unit (MCU) communicatively coupled to the IMU and configured to calculate first feature-related data and second feature-related data from the motion and acoustic signatures, and a machine learning service executing on the MCU. The machine learning service includes a trained and programmed machine language model configured to receive the first and second feature-related data, generate a predicted detection of scratching activity by performing a first machine-learning operation on the first feature-related data, generate a predicted detection that the human subject is asleep using the second feature-related data, and classify each instance of predicted scratching activity according to whether the human subject is predicted to be asleep or awake at the time of the scratching activity.

In some embodiments, the classification of each instance of predicted scratching activity distinguishes scratching activity occurring during a predicted sleep state from scratching activity occurring during a predicted awake state. In some embodiments, the detection of human scratching activity comprises detecting a start of the scratching activity, associating time one with the start, detecting an end of the scratching activity, and associating time two with the end. In some embodiments, the MCU calculates a scratch duration by subtracting time one from time two.

In some embodiments, a pattern of vibratory motor operation is determined based on whether the subject is predicted to be asleep

According to another aspect, embodiments relate to a method. The method comprises providing a sensor including an inertial measurement unit (IMU) configured to be in direct mechanical communication with the skin of a human subject and a microcontroller unit (MCU) communicatively coupled to the IMU and including a machine learning service; measuring motion and acoustic signatures of physiological processes of the human subject solely through the IMU; calculating first feature-related data and second feature-related data by the MCU from the measured motion and acoustic signatures; sending the calculated feature-related data to the machine learning service executing locally on the sensor; determining a predicted detection of scratching activity with the machine-learning service by performing a first machine-learning operation on the first feature-related data; determining a predicted detection that the human subject is asleep based on the second feature-related data; and classifying each instance of predicted scratching activity according to whether the human subject is predicted to be asleep or awake at the time of the scratching activity.

In some embodiments, the method further comprises providing haptic feedback to the human subject upon detecting human scratching activity. In some embodiments, the method further comprises energizing a vibratory motor via the MCU when human scratching activity is detected.

According to another aspect, embodiments relate to an electronic device for measuring motion and acoustic signatures of physiological processes of a human subject. The device comprises an IMU for detecting the motion and acoustic signatures, the IMU configured to be operably in direct mechanical communication with the skin of the human subject; a MCU communicatively coupled to the IMU, the MCU configured to calculate first feature-related data and second feature-related data from the motion and acoustic signatures; and a machine learning service executing on the MCU. The machine learning service includes a trained and programmed machine language model configured to: receive the first feature-related data and the second feature-related data calculated by the MCU; and generate a predicted detection of scratching activity of the human subject by performing a first machine-learning operation using the first feature-related data received from the MCU. The first machine-learning operation includes at least one neural network flow.

In some embodiments, the second feature-related data is used to determine an intensity of the predicted detection of scratching activity. In some embodiments, the human subject suffers from one or more of pruritus associated with cutaneous T-cell lymphoma (CTCL), renal failure, urticaria, diabetes, and chronic pruritus of the elderly.

According to another aspect, embodiments relate to a method that comprises providing a sensor including an IMU configured to be in direct mechanical communication with the skin of a human subject and a MCU communicatively coupled to the IMU and including a machine learning service; and measuring motion and acoustic signatures of physiological processes of a human subject solely through the IMU. The method further comprises calculating first feature-related data and second feature-related data of the human subject by the MCU from the motion and acoustic signatures measured by the IMU; sending the calculated first feature-related data and the second feature-related data to the machine learning service executing locally on the sensor; and determining a predicted detection of scratching activity with the machine-learning service by performing a first machine-learning operation using a machine language model of the machine learning service on the received first feature-related data. The first machine-learning operation may involve at least one neural network flow.

Various embodiments are described more fully below with reference to the accompanying drawings, which form a part hereof, and which show specific exemplary embodiments. However, the concepts of the present disclosure may be implemented in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided as part of a thorough and complete disclosure, to fully convey the scope of the concepts, techniques and implementations of the present disclosure to those skilled in the art. Embodiments may be practiced as methods, systems or devices. Accordingly, embodiments may take the form of a hardware implementation, an entirely software implementation or an implementation combining software and hardware aspects. The following detailed description is, therefore, not to be taken in a limiting sense.

Reference in the specification to “one embodiment” or to “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiments is included in at least one example implementation or technique in accordance with the present disclosure. The appearances of the phrase “in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment. The appearances of the phrase “in some embodiments” in various places in the specification are not necessarily all referring to the same embodiments.

Some portions of the description that follow are presented in terms of symbolic representations of operations on non-transient signals stored within a computer memory. These descriptions and representations are used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. Such operations typically require physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical, magnetic or optical signals capable of being stored, transferred, combined, compared and otherwise manipulated. It is convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like. Furthermore, it is also convenient at times, to refer to certain arrangements of steps requiring physical manipulations of physical quantities as modules or code devices, without loss of generality.

However, all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated otherwise as apparent from the following discussion, it is appreciated that throughout the description, discussions utilizing terms such as “processing” or “computing” or “calculating” or “determining” or “displaying” or the like, refer to the action and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system memories or registers or other such information storage, transmission or display devices. Portions of the present disclosure include processes and instructions that may be embodied in software, firmware or hardware, and when embodied in software, may be downloaded to reside on and be operated from different platforms used by a variety of operating systems.

The present disclosure also relates to an apparatus for performing the operations herein. This apparatus may be specially constructed for the required purposes, or it may comprise a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer. Such a computer program may be stored in a computer readable storage medium, such as, but is not limited to, any type of disk including floppy disks, optical disks, CD-ROMs, magnetic-optical disks, read-only memories (ROMs), random access memories (RAMs), EPROMs, EEPROMs, magnetic or optical cards, application specific integrated circuits (ASICs), or any type of media suitable for storing electronic instructions, and each may be coupled to a computer system bus. Furthermore, the computers referred to in the specification may include a single processor or may be architectures employing multiple processor designs for increased computing capability.

The processes and displays presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose systems may also be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform one or more method steps. The structure for a variety of these systems is discussed in the description below. In addition, any particular programming language that is sufficient for achieving the techniques and implementations of the present disclosure may be used. A variety of programming languages may be used to implement the present disclosure as discussed herein.

In addition, the language used in the specification has been principally selected for readability and instructional purposes and may not have been selected to delineate or circumscribe the disclosed subject matter. Accordingly, the present disclosure is intended to be illustrative, and not limiting, of the scope of the concepts discussed herein.

Pruritus, or more informally “itch,” is a symptom common to several medical conditions. These conditions may range from dermatologic pathologies to systemic diseases such as, and without limitation, renal failure, urticaria, diabetes, chronic pruritus of the elderly, and malignancies like cutaneous T-cell lymphoma (CTCL).

Acute and chronic itch affects between 8% and 14% of the population, respectively, and can adversely affect quality of life. The itch-scratch cycle generally starts with an itch, which triggers scratch, which in turn causes further itch, inflammation, and infection.

This scratching behavior can become habitual. Habitual scratching can be particularly troublesome if scratching occurs during sleep, which is essential for proper developmental growth, physical growth, mental health, and general well-being. However, nighttime scratching may disrupt sleep quality and cause or at least contribute to the onset of sleep disorders.

Existing techniques for evaluating itch involve administering or otherwise providing patients with subjective surveys involving numeric grading scales. There is poor correlation between actual scratching activity behavior and observed scratching behavior, however. Additionally, results of these surveys may be of questionable value because different patients may have different tolerances or sensitivity to different severities of itch.

Another existing approach for evaluating itch involves direct visualization of scratching with video recordings. However, this is time-consuming, impractical, and intrusive to users.

1 FIG. 100 100 100 100 Embodiments described herein provide exemplary systems and methods for evaluating itch, detecting scratching activity, classifying scratching events by sleep state, and providing therapeutic biofeedback.illustrates an acousto-mechanic, wearable electronic devicein accordance with one embodiment. In some embodiments, the electronic device(hereafter “device”) may be physically embodied in the form of a sensor that may be operably positioned with respect to a person's skin to gather physiological data, behavior data, or the like. Specifically, the devicemay capture low-frequency data corresponding to motion and high-frequency data corresponding to a wide variety of clinical biomarkers.

100 102 104 106 102 102 102 The devicemay include a base portion, an electronics board, and a top portion. The bottom portionmay include or be configured as a waterproof, silicone portion that may attach to a user's hand or other body location. Additionally, the bottom portionshould be soft and flexible such that it can adapt to movements of the user's hand and remain in operable contact with the user's hand during movement. The bottom portionmay remain in operable contact with the user at least in part due to an adhesive.

102 102 100 In some embodiments, the base portionmay attach to dorsal side of a user's hand. For example, the base portionmay be positioned over the metacarpal bones associated with a user's index finger and middle finger. In this location, the devicemay detect low and high frequency signals resulting from the user performing a scratching or rubbing motion with one or more of their fingers, wrist, hand, etc.

100 Upon predicting the detection of scratching activity (e.g., determining that a user is performing a scratching activity or at least likely performing a scratching activity), the devicemay provide haptic feedback to the user. This haptic feedback may alert the patient of the scratching activity (including unconscious scratching activity) to encourage the user to cease scratching.

104 108 110 112 114 100 The electronics boardmay include or otherwise support several components. These may include but are not limited to a microcontroller, power source, accelerometer, a haptic feedback providersuch as a haptic motor, and wireless charging circuitry. The devicetherefore provides multiple hardware components in a compact space to minimize the form factor and maximize usability and practicality of the device with low power consumption and longer operation.

106 106 The top portionmay be formed of or otherwise include a soft, stretchable, and water-proof material. The top portionshould also be able to flex to accommodate movement of the user's hand or other body portion.

2 FIG. 1 FIG. 1 FIG. 2 FIG. 2 FIG. 200 104 104 202 204 108 206 210 212 illustrates a diagramof the electronics boardofin accordance with one embodiment. Components shown inare presented inusing the same reference numerals. The electronics boardinmay include a microcontroller unit (MCU), an inertial measurement unit (IMU), a power source, a power management unit (), a storage, and a haptic feedback provider.

202 214 216 218 220 202 100 100 100 The MCUmay execute or otherwise include memory, an interface, one or more machine learning models, and general-purpose input-outputs (GPIO(s)). The MCUmay be located on-board with the deviceso that the required analytics are performed on the device. In some embodiments the machine learning service executes entirely locally on the device.

204 110 110 110 The IMUmay include or otherwise execute one or more accelerometers. The accelerometer(s)may measure acceleration along the x- and y-axes at 200 Hz. The accelerometer(s)may measure acceleration in the z-axis up to 1,600 Hz. Acceleration in these directions may indicate movement such as scratching activity, for example.

202 202 214 214 214 204 202 The MCUincludes various combinations of resistors, transistors, and diodes to form any number of logic gates to execute appropriate programs. The MCUmay store any combination of types of memorysuch as RAM memory configurations. The memorymay include non-volatile memory such as flash memory, EPROM, EEPROM, ROM, and PROM, or volatile memory such as static or dynamic RAM, as discussed above. The exact configuration/type of onboard memorymay of course vary as long as instructions for analyzing data from the IMUmay be performed by the MCU.

218 218 204 218 The machine learning model(s)may execute one or more of a variety of machine learning modelsto analyze data gathered by and provided from the IMU. One or more machine learning modelsmay have been trained on data from clinical studies monitoring scratching activity.

For example, data regarding scratching activity events may be collected from various body sites over a period of time. These body sites may include, but are not limited to, the dorsal hand, head, forearm, inner elbow, thigh, and calf. Non-scratching movements may also be considered during a training phase, and may include activities such as waving, texting, tapping, movements associated with restlessness, etc.

220 212 212 112 222 Upon detecting scratching activity, the GPIO(s)may communicate a signal to the haptic feedback provider. The haptic feedback providermay then provide haptic feedback to the user. The haptic feedback providermay include an eccentric rotating mass (ERM) motorto create vibrations.

222 In some embodiments, the motormay be configured to rotate at 10,000 rpm to generate 1.4 G of vibratory feedback. Regardless of the exact amount of vibratory feedback provided, the vibratory feedback should be sufficient to alert users, even during sleep.

112 230 220 202 230 222 112 112 The haptic feedback providermay be powered by a voltage regulatorthat is controlled by the (GPIO) pinfrom the MCU. For example, the voltage regulatormay use pulse width modulation to create feedback of variable strength, duration, or some combination thereof. Pulse width modulation utilizes pulses of varying widths to create a cycle that may modulate the rotation speed of the motor. Using this configuration, the haptic feedback providermay generate several types of haptic profiles. For example, the haptic feedback providermay generate profiles with gentle vibrations, intense vibrations, ramping effects, short bursts, etc., even during sleep.

108 104 108 The power sourcemay be any sort of power source to supply power to the components of the board. In some embodiments, the power sourcemay be a rechargeable Li-polymer or Li-ion batteries.

210 The storagemay store data regarding the user and signals appropriate for the user. For example, a particular user may require a haptic signal that is intense and in spurts to detect the haptic signal. Accordingly, the haptic profiles or otherwise the type of haptic feedback provided may vary and may depend on the user, the message intended to be conveyed, etc. For example, feedback may vary in length, intensity, pattern(s), or some combination thereof.

212 Similarly, users may select their most preferred haptic feedback to minimize aggravation or mitigate habituation. For example, some users may not notice or respond to a low-intensity vibration from the haptic feedback provider. Accordingly, some users may prefer to receive a higher intensity vibration.

Additionally or alternatively, some users may find high intensity vibrations jarring or disruptive. Accordingly, some users may prefer to receive a lower intensity vibration.

100 100 1 FIG. Data regarding sleeping patterns, scratching activity and other user behavior may have been previously gathered. As part of a training phase, a user wearing the devicemay have been asked to perform a scratching activity on a devicein the form of a force sensor (not shown in).

100 For example, a user may wear the force sensor (e.g., device) and apply a scratching motion on a force resistive resister (“FSR”). The surface of the force sensor may be covered with an aluminum foil to make the coefficient of friction (“COF”) of the surface similar to the dorsal hand (“DH”). The FSR may detect the force applied to its surface during the test scratching activity (i.e., while the user is scratching the surface of the FSR). As the user is wearing the force sensor during the test scratching activity, the accelerometer of the force sensor may simultaneously gather acceleration data related to the user's movement.

The applied force may represent an intensity level of the scratch activity. That is, the higher the detected force resultant from a scratch activity, the more intense the scratch activity.

3 FIG. 300 300 100 presents a graphshowing the relationship between frequency and force. The graphalso illustrates the Spearman correlation to show the relationship between scratch intensity (measured in force (N)) and the sensor signal of device, embodied as the force sensor in this example. For each trial, the speed of scratching and the angle between the finger and the surface of the FSR were maintained constant. The power of the scratch signal collected by the force sensor can then be computed. As scratch intensities increase, the power of the signal between 40 Hz and 60 Hz would increase.

4 FIG. 400 400 presents a graphical representationof different scratching activities detected over a time period. As seen in graphical representation, acceleration data of scratching activity of varying intensities is detected over a time period. As scratch intensities increase, the power of the signal between 40 Hz and 60 Hz would increase.

204 110 In operation, the IMUmay gather data regarding user activity. For example, and as discussed above, the accelerometer(s)may gather acceleration data in various axes to identify behavior that may indicate scratching activity.

218 218 204 218 The machine learning model(s)may execute one or more of a variety of machine learning modelsto analyze data from the IMU. One or more machine learning modelsmay have been trained on data from clinical studies monitoring scratching activity.

100 100 For example, scratching activity training events may be collected from healthy individuals who are at least 18 years old and having no skin allergies to adhesive or current skin irritation near anticipated sensor sites on deviceto develop a machine learning algorithm. For detecting these scratching activity events, the devicemay be placed on the dorsal hand of the participant along their second digit metacarpal bone using a skin adhesive. Each participant may perform scratching activities for 35 seconds and nonscratching activities for 65 seconds. The participants may perform multiple scratching activities over clothing (e.g., on their abdomen, thigh, calf, knee, and shoulder), and may perform multiple scratching activities directly on skin (e.g., on their cheek, head, inner elbow, outer elbow, forearm, back of hand, and palm).

218 218 204 The machine learning model(s)may include one or more of random forest classifiers, logistic regression, neural networks, or the like. The exact type of machine learning model(s)used may vary as long as they can analyze data from the IMUto identify scratching activity.

5 FIG. 500 204 218 500 500 500 500 218 502 504 506 508 illustrates a workflowfor analyzing data from the IMUin accordance with one embodiment. One or more machine learning modelsmay perform the workflowor at least part of the workflow. The workflowor at least part of the workflowmay be used to train one or more aspects of a machine learning model. This particular model may include a signal processing block, a convolutional recurrent neural network (“CRNN”), a classification moduleand a clustering module.

502 510 512 Training data obtained from subjects performing scratching and non-scratching behaviors may first be sent to processing block. This may be z-axis acceleration data and a sliding window modulemay divide the acceleration data into a plurality of groups. For example, in some embodiments, the raw time series data of z-axis acceleration may be segmented into 320-milisecond (512 data points) frames, using a window with 75% overlap between adjacent frames. A fast Fourier transform modulemay then compute a short-time Fourier transform (“STFT”) features.

504 514 516 518 The CRNNmay then receive and process these features through one or more 1-D convolutional layers, linear layers, and a gated recurrent unit (“GRU”)layer analyzing temporal patterns of signals.

504 520 522 The output of the of the CRNNmay then be provided to a fully connected neural networkfor classification. For example, predicted outputs may be clustered using a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. For example, a sigmoid functionmay classify activity as scratching activity or non-scratching activity depending on the associated feature data.

6 FIG. 600 600 204 illustrates a graphical representation of a sigmoid functionin accordance with one embodiment. The sigmoid functionmay represent a probability that particular activity, based on the feature related data on the x-axis, indicates scratching activity. The x axis may correspond to, for example, acceleration data obtained from the IMU.

602 602 506 A user or administrator (e.g., medical personnel) may specify a decision boundarysuch that feature(s) that place activity to the right of the boundaryhave a higher probability of being a scratching activity than being non-scratching activity. Accordingly, the classification modulemay classify this activity as scratching activity.

600 204 602 602 In other words, the sigmoid functionrepresents the probability that particular activity, as determined by data from the IMU, represents scratching activity. Activity with features to the right of the boundarymay be classified as scratching activity, and activity with features to the left of the boundarymay be classified as non-scratching activity.

500 522 506 The workflowmay be used to classify activity at least substantially in real time. The sigmoid functionmay then classify the activity as scratching or non-scratching based on output from the neural network. The clustering modulemay then cluster the feature-related data by, for example, executing the DBSCAN algorithm.

100 As one aspect, the embodiments described herein allow for in-sensor computation of the CRNN model using edge computing. Based on the CRNN model developed, the devicemay use a fixed size queue of 512 data points (320 milliseconds with 1,600 Hz sampling rate) may be defined to replicate the frames of the CRNN model. Once the queue is full, the data contained in the queue may be passed to the signal processing block to compute the STFT. The STFT may then be passed to the CRNN model. For every new incoming data point, the oldest data point is removed, and the new data point is added to the queue via a first in, first out (FIFO) scheme. Computation of scratch detection may be then repeated for every 128 new data points.

7 FIG. 700 204 As another example, the embodiments herein may use random forest-based machine learning models to classify activity as scratching activity. For example,illustrates a random forest classifierthat receives feature-related data from the IMU.

700 1 700 The random forest classifiermay include a plurality of trees that are each configured to detect whether some feature(s) are present or otherwise associated with identified activity. For example, treemay first consider whether activity such as acceleration in the z axis above some threshold is detected (e.g., whether the user is likely sleeping, whether the acceleration occurred a threshold number of times, etc.). If so, the classifiermay traverse a certain branch of the tree

7 FIG. Certain nodes of the trees are darkened indicating the presence or absence of some particular feature. Although three trees are illustrated in, any number of trees may be used to consider any number of features.

Each tree may output a classification decision regarding whether the activity is predictive of scratching activity. These predictions are based on the presence or absence of certain features.

704 706 The classification decisions of one or more trees may be combined in step. A classification decision is then provided in step.

The above-discussed examples and illustrations of machine learning models are exemplary. Other types of machine learning models may be used, such as support vector machines, logistic regression-based models, or the like.

2 FIG. 220 212 222 100 Referring back to, upon detecting scratching activity, the GPIO(s)may issue a signal to the haptic feedback providerto provide haptic feedback to the user. For example, the motormay cause the deviceto vibrate with some form, intensity, duration, or the like.

The user may detect or feel this vibration, which they may associate with scratching activity. For example, the vibration may remind the user they are scratching themselves, and may encourage the user to cease scratching.

100 100 As discussed above, the user may be sleeping while wearing the device. During sleep, the user may subconsciously scratch themselves. The devicemay nonetheless provide this haptic feedback, which may encourage the user to, albeit at least partially subconsciously, cease the scratching activity.

8 FIG. 1 FIG. 800 100 800 depicts a flowchart of a methodfor monitoring user activity in accordance with one embodiment. The deviceofor components thereof may perform one or more of the steps of method.

802 Stepinvolves measuring motion and acoustic signatures of physiological processes of a human subject. A human subject (for simplicity “user”) may have been diagnosed with a medical condition for which itch is a symptom. Accordingly, the user may have a tendency or desire to scratch one or more locations on their body. As discussed previously, the scratching may exacerbate the symptom or condition.

The user need not have been diagnosed, either. Rather, the user may want to curb their scratching activity on their own, even without a diagnosis from medical personnel.

100 100 The user may place a sensor such as the deviceon a location of their body, such as on their dorsal hand between the second and third metacarpal bones. Alternatively, medical personnel may place the deviceon the user.

100 The devicemay continuously measure motion and acoustic signatures of physiological processes of a human subject, such as during sleep, during a medical examination, or the like. For example, the user may want to be deterred from performing scratching activity during sleep.

804 202 2 FIG. Stepinvolves calculating a first feature-related data from the motion and acoustic signatures. An MCU such as the MCUofmay analyze received raw data regarding motion and acoustics associated with the user.

806 Stepinvolves sending the first feature-related data to a machine learning service. The machine learning service may include any of the types of models discussed previously, as well as any other type of model available now or formulated hereafter.

808 808 Stepinvolves determining a detection of human scratching activity by the machine learning service by performing a machine learning operation on the feature-related data. Stepmay involve executing one or more machine learning models to determine whether the feature-related data indicates or at least suggests that the user is performing a scratching activity. For example, the machine learning model(s) may rely on previously-gathered data associated with known scratching activity.

810 Upon detecting scratching activity, stepinvolves providing haptic feedback to the user to encourage them to cease the scratching activity—whether they are sleeping or are awake. Accordingly, the embodiments herein provide a therapeutic biofeedback tool for itch.

100 100 The application of low-power, high fidelity, AI-based analytics integrated into epidermal sensors with skin-friendly adhesives such as with the devicefor long-term wear maximizes clinical potential and relevancy. The integration of machine learning analytics with haptic feedback on the deviceprovides a closed loop modality to quantify scratch events and provide real-time accurate feedback to improve patient outcomes. This technology can serve as a platform to classify and provide feedback to patients suffering from a wide array of dermatological disorders and co-morbidities and to help guide and assess efficacy of treatment plans.

The methods, systems, and devices discussed above are examples. Various configurations may omit, substitute, or add various procedures or components as appropriate. For instance, in alternative configurations, the methods may be performed in an order different from that described, and that various steps may be added, omitted, or combined. Also, features described with respect to certain configurations may be combined in various other configurations. Different aspects and elements of the configurations may be combined in a similar manner. Also, technology evolves and, thus, many of the elements are examples and do not limit the scope of the disclosure or claims.

Embodiments of the present disclosure, for example, are described above with reference to block diagrams and/or operational illustrations of methods, systems, and computer program products according to embodiments of the present disclosure. The functions/acts noted in the blocks may occur out of the order as shown in any flowchart. For example, two blocks shown in succession may in fact be executed substantially concurrent or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Additionally, or alternatively, not all of the blocks shown in any flowchart need to be performed and/or executed. For example, if a given flowchart has five blocks containing functions/acts, it may be the case that only three of the five blocks are performed and/or executed. In this example, any of the three of the five blocks may be performed and/or executed.

A statement that a value exceeds (or is more than) a first threshold value is equivalent to a statement that the value meets or exceeds a second threshold value that is slightly greater than the first threshold value, e.g., the second threshold value being one value higher than the first threshold value in the resolution of a relevant system. A statement that a value is less than (or is within) a first threshold value is equivalent to a statement that the value is less than or equal to a second threshold value that is slightly lower than the first threshold value, e.g., the second threshold value being one value lower than the first threshold value in the resolution of the relevant system.

Specific details are given in the description to provide a thorough understanding of example configurations (including implementations). However, configurations may be practiced without these specific details. For example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary detail in order to avoid obscuring the configurations. This description provides example configurations only, and does not limit the scope, applicability, or configurations of the claims. Rather, the preceding description of the configurations will provide those skilled in the art with an enabling description for implementing described techniques. Various changes may be made in the function and arrangement of elements without departing from the spirit or scope of the disclosure.

Having described several example configurations, various modifications, alternative constructions, and equivalents may be used without departing from the spirit of the disclosure. For example, the above elements may be components of a larger system, wherein other rules may take precedence over or otherwise modify the application of various implementations or techniques of the present disclosure. Also, a number of steps may be undertaken before, during, or after the above elements are considered.

Having been provided with the description and illustration of the present application, one skilled in the art may envision variations, modifications, and alternate embodiments falling within the general inventive concept discussed in this application that do not depart from the scope of the following claims.